An Empirical Study on Large-Scale Content-Based Image Retrieval
Conference Proceeding Article
One key challenge in content-based image retrieval (CBIR) is to develop a fast solution for indexing high-dimensional image contents, which is crucial to building large-scale CBIR systems. In this paper, we propose a scalable content-based image retrieval scheme using locality-sensitive hashing (LSH), and conduct extensive evaluations on a large image testbed of a half million images. To the best of our knowledge, there is less comprehensive study on large-scale CBIR evaluation with a half million images. Our empirical results show that our proposed solution is able to scale for hundreds of thousands of images, which is promising for building Web-scale CBIR systems.
Computer Sciences | Databases and Information Systems
Data Management and Analytics
IEEE International Conference on Multimedia and Expo, 2007: ICME 2007: 2 - 5 July 2007, Beijing, China: Proceedings
City or Country
WONG, Yuk Man; HOI, Steven C. H.; and LYU, Michael R..
An Empirical Study on Large-Scale Content-Based Image Retrieval. (2007). IEEE International Conference on Multimedia and Expo, 2007: ICME 2007: 2 - 5 July 2007, Beijing, China: Proceedings. 2206-2209. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/2386